P-Video-2
P-Video-2 is Pruna AI's quality-focused successor to P-Video, creating clips from text, images, or audio-conditioned inputs through one model. It produces sharper close-ups and foreground subjects, stronger identity and input-image consistency, improved lip synchronization for natively generated speech, and clearer on-screen text while generating dialogue, music, and sound effects with the video. It supports optional first-and-last-frame guidance, draft iteration, durations up to 20 seconds, 720p or 1080p output, and 24 or 48 FPS.
Driving a clip from your own audio How to condition Pruna P-Video-2 on an imported track with inputs.audio, why the audio and not duration sets the length, and when to import a voice instead of generating one.
Draft mode and reproducible reruns How to use settings.draft in Pruna P-Video-2 to test a direction cheaply, what it changes besides quality, and why an approved draft cannot be promoted to a final.
Pinning the first and last frame How to give Pruna P-Video-2 both ends of a shot, how far apart the two stills can sit before the transition breaks, and the pairing trick that produces a seamless loop.
Animating a still with a first frame How to drive Pruna P-Video-2 from an image with inputs.frameImages, why the still and not your parameters decides the output shape, and how to hold a product across a variant set.
Native audio, dialogue and lip sync How to direct the sound P-Video-2 generates with the picture: ambience, effects, music beds, and spoken lines that the mouth actually matches.
Writing prompts for scene, motion and sound How to write prompts for Pruna P-Video-2, from the clause order the model reads to the framing, camera motion and sound directions that ship inside the same string.
Resolution, aspect ratio, frame rate and length How to size a Pruna P-Video-2 clip: the two mutually exclusive ways to state dimensions, the fourteen accepted pairs, what 48 fps buys, and what happens when you omit duration.